About this position
Do you want to develop a foundation model for one of biology’s most complex ecosystems? By joining the European Innovation Council (EIC) Pathfinder project NOAH, you will design, train and implement ARCA: an AI foundation model for crop microbiomes. You will work at the interface of deep learning, bioinformatics and microbial ecology, using large-scale microbiome and genome data to learn contextual representations of microbes and communities and translate them into predictive models for successful crop microbiome engineering.
Your job Plant-associated microbiomes can strongly influence crop growth, nutrition and resilience, but their behaviour depends on the crop, soil, environment and the surrounding microbial community. NOAH aims to make these context-dependent interactions learnable and predictable. At the centre of the project is ARCA (AI-guided Root microbiome engineering for ClimAte-resilient and nutritious crops), a crop microbiome foundation model trained on large-scale public and newly generated datasets.
As Postdoctoral Researcher in AI, you will take a leading technical role in developing ARCA. You will explore which model architectures and learning objectives work best for sparse, high-dimensional and heterogeneous microbiome data, and turn the selected approaches into robust trainable models. Your work will cover both foundation-model pretraining and downstream predictive and generative applications.
Your main responsibilities are to: design, implement and benchmark foundation-model architectures for microbiome data, including transformer-based and masked-autoencoder approaches and relevant architectures adapted from related biological domains; develop representations that integrate microbial identity and abundance with genomic or functional information and contextual metadata such as crop genotype, soil and environmental conditions; define and evaluate self-supervised learning objectives and embedding strategies, and benchmark their added value against simpler machine-learning baselines; train and evaluate ARCA on large-scale microbiome datasets, with attention to sparsity, batch effects, scalability, generalisation across studies and uncertainty in downstream predictions; fine-tune ARCA for tasks including microbial root competence and crop-relevant outcomes, and iteratively improve the model using experimental Design-Build-Test-Learn data generated by NOAH partners; develop a generative ARCA component, exploring autoencoder- and/or diffusion-based approaches for generating ecologically plausible microbiome configurations; apply interpretable and explainable AI approaches to identify microbial taxa, functions and contextual features driving model predictions; develop reproducible training and evaluation workflows and work with project partners to make models and associated tools usable beyond the immediate research setting. You will not work on an isolated AI benchmark. ARCA predictions will be tested experimentally in greenhouse and field settings and the resulting microbiome and crop phenotype data will feed back into model development.
This gives you the opportunity to develop new AI methodology while seeing how model predictions perform in a real biological and agricultural system. In this position you will part of an interdisciplinary research environment spanning the AI Technology for Life and Plant-Microbe Interactions groups, with close interaction with bioinformatics, microbial ecology and experimental crop research at the UU and NOAH partners. You will have access to Utrecht University GPU/HPC infrastructure and large, curated microbiome and microbial genome datasets.
Additionally, you will collaborate closely with NOAH partners at Aarhus University, Niab, INRAE and The Hyve, including experimental teams that will directly test model predictions.
Requirements
- Specific Requirements We are looking for a postdoctoral researcher who enjoys developing methods for complex biological data and working closely with experimental scientists.
- You meet the following criteria: a PhD, or a PhD close to completion, in machine learning, artificial intelligence, computational biology, bioinformatics, computer science or a closely related field; strong hands-on experience with deep learning and modern representation learning, preferably including transformers, self-supervised learning, foundation models, autoencoders or related architectures; strong programming skills in Python and experience with a deep-learning framework such as PyTorch, including training and evaluating models on GPU/HPC infrastructure; experience working with high-dimensional biological, omics, ecological or similarly sparse and heterogeneous data, or a clear motivation to develop this expertise; an interest in interpretable AI, rigorous benchmarking and reproducible research, together with the ability to collaborate across AI, bioinformatics, microbiology and crop science.
- Experience with microbiome data, microbial genomics, metagenomics or multimodal biological data is an advantage, but is not required if you bring strong machine-learning expertise and are motivated to learn the biology.
How to apply
- Read the full advert on the source site — it carries the authoritative terms.
- Prepare your SOP, CV, transcripts and referees before the deadline.
- Apply through the university's own portal. Never pay a fee to a third party.